text-detection-0004

Use Case and High-Level Description

Text detector based on PixelLink architecture with MobileNetV2, depth_multiplier=1.4 as a backbone for indoor/outdoor scenes.

Example

Specification

Metric

Value

F-measure (Harmonic mean of precision and recall on ICDAR2015)

79.43%

GFlops

23.305

MParams

4.328

Source framework

TensorFlow*

Inputs

Image, name: Placeholder, shape: 1, 768, 1280, 3 in the format B, H, W, C, where:

  • B - batch size

  • H - image height

  • W - image width

  • C - number of channels

Expected color order: BGR.

Outputs

  1. name: model/link_logits_/add, shape: 1, 192, 320, 16 - logits related to linkage between pixels and their neighbors.

  2. name: model/segm_logits/add, shape: 1, 192, 320, 2 - logits related to text/no-text classification for each pixel.

Refer to PixelLink and demos for details.

Demo usage

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities: